ReDMark: Framework for residual diffusion watermarking based on deep networks

作者：

Highlights：

• Learning new embedding patterns.

• Customizing solutions for suggested transform domains and attacks.

• Enhancing security and robustness by diffusing watermark in a wide area of images.

摘要

•Learning new embedding patterns.•Customizing solutions for suggested transform domains and attacks.•Enhancing security and robustness by diffusing watermark in a wide area of images.

论文关键词：Blind watermarking,CNN,Data diffusion,Deep convolutional networks,FCN,Transparency

论文评审过程：Received 15 February 2019, Revised 15 July 2019, Accepted 20 December 2019, Available online 25 December 2019, Version of Record 7 January 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.113157